Representation Learning of Knowledge Graphs with Hierarchical Types

By Ruobing Xie, Zhiyuan Liu, Maosong Sun. 2016

332 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Hongwei Wang
2. Fuzheng Zhang
3. Liang Yao
4. Xing Xie
5. Xu Han
6. Miao Zhao
7. Zhiyuan Liu
8. Vincent Wenchen Zheng

Citations in the corpus

• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, methodology): “ and requires Mr = diag(r). The scoring function is hence defined as fr(h,t)= h⊤diag(r)t = ˝ d i=1 [r]i ·[h]i ·[t]i. Researchers also propose incorporating auxiliary information, such as entity types [39], logic rules [21], and textual descriptions [46] to assist KGE. However, these methods are more”
• A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, background): “A specific application which is popularly discussed in knowledge graph embedding is entity ranking [51], [52], [53], [59], [61] .”
• GRAM: Graph-based Attention Model for Healthcare Representation Learning (2016, background): “They aim to project entities and relations (Bordes et al., 2013; Socher et al., 2013; Wang et al., 2014; Lin et al., 2015) to the latent space based on the triples or additional information such as hierarchy of entities (Xie et al., 2016).”
• Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba (2018, methodology): “e with similar side information should be closer in the embedding space. To achieve this, a joint framework is proposed to optimize the embeddingobjectivefunctionwithaclassifierfunction[11,20].And in [25] Xie et al. further embedded a complicate knowledge graph with the node in a hierarchical struct”
• Analogical Inference for Multi-relational Embeddings (2017, unknown): “…et al., 2012) 81.6 33.1 TransH (Wang et al., 2014) 86.7 64.4 TransE (Bordes et al., 2013) 89.2 47.1 TransR (Lin et al., 2015b) 92.0 68.7 TKRL (Xie et al., 2016) – 73.4 RTransE (Garcia-Duran et al., 2015) – 76.2 TransD (Ji et al., 2015) 92.2 77.3 CTransR (Lin et al., 2015b) 92.3 70.2 KG2E (He…”
• Learning Entity Type Embeddings for Knowledge Graph Completion (2017, methodology): “We also collected entity types that are mapped to entities in both datasets from [15] for FB15k and the YAGO taxonomy1 for YAGO43k.”
• Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention (2018, methodology): “Furthermore, the hierarchical information of entities in KGs has also been utilized and demonstrated to be effective for model enhancement (Hu et al., 2015; Xie et al., 2016).”
• Augmenting Neural Machine Translation with Knowledge Graphs (2019, background): “, 2016a) as well as TKRL (Xie et al., 2016b).”
• Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction (2019, background): “Although there exists some work that takes the hierarchy structures into account (Xie, Liu, and Sun 2016; Zhang et al. 2018), they usually require additional data or process to obtain the hierarchy information.”
• Knowledge Graph Embedding: A Survey of Approaches and Applications (2017, background): “[26] devised type-embodied knowledge representation learning (TKRL), which can handle hierarchical entity categories and multiple category labels.”
• Quantifying Similarity between Relations with Fact Distribution (2019, background): “…al., 2009; Etzioni et al., 2011; Saha et al., 2017) and relation extraction (Riedel et al., 2013; Liu et al., 2013; Zeng et al., 2014; Santos et al., 2015; Zeng et al., 2015; Lin et al., 2016), and relation prediction (Bordes et al., 2013; Wang et al., 2014; Lin et al., 2015b,a; Xie et al., 2016).”
• Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation (2019, methodology): “le, for a given knowledge triple (h,r,t), we first utilize multiple cross&compress units and nonlinear layers to process the raw feature vectors of head h and relation r (including ID [13], types [36], textual description [35], etc.), respectively. Their latent features are then concatenated tog”
• KG-BERT: BERT for Knowledge Graph Completion (2019, methodology): “Text-enhanced models DKRL and SSP can also outperform structure only methods TransE and TransH.”